© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 1998
    Prev
    Next
    INDEX
    Explanations

    playful, play, games

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ女åĦ¿
    -0.09
    éĿ¢èī²
    -0.09
    andin
    -0.09
    ä¿¡æģ¯åĮĸ
    -0.08
    ÅĽl
    -0.08
    èĦ¸èī²
    -0.08
    温æ³ī
    -0.08
    paced
    -0.08
    ination
    -0.08
    ages
    -0.08
    POSITIVE LOGITS
    ingly
    0.10
    ç¨ļ
    0.10
    å¤©çľŁ
    0.09
    è¯Ļ
    0.09
    磾
    0.09
    对å¾ħ
    0.09
    .moveTo
    0.09
    esen
    0.09
    inks
    0.09
    ãģĦãģĨ
    0.08
    Activations Density 0.006%

    No Known Activations